ChandlerBang/Pro-GNN
Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"
This project helps machine learning researchers and practitioners make their Graph Neural Networks (GNNs) more reliable and trustworthy. It takes a GNN model and a potentially 'attacked' or corrupted graph, then outputs a more robust GNN that can make accurate predictions even when the graph data has been tampered with. This is for those working with GNNs in sensitive areas who need to ensure their models aren't fooled by adversarial attacks.
304 stars. No commits in the last 6 months.
Use this if you are developing or deploying Graph Neural Networks and need to protect them from intentional data perturbations or adversarial attacks that could lead to incorrect predictions.
Not ideal if you are working with non-graph data or are not concerned with the robustness of your GNNs against adversarial attacks.
Stars
304
Forks
47
Language
Python
License
—
Category
Last pushed
May 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ChandlerBang/Pro-GNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Trusted-AI/adversarial-robustness-toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion,...
bethgelab/foolbox
A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
DSE-MSU/DeepRobust
A pytorch adversarial library for attack and defense methods on images and graphs
cleverhans-lab/cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
BorealisAI/advertorch
A Toolbox for Adversarial Robustness Research